Searcharxiv⌕ Search

arXiv subjects

Zihan Chen

Publications and source records attributed to Zihan Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

Leveraging Phase Polynomials for Quantum Circuit Optimization

Quantum circuits on resource-limited hardware require optimizing regions dominated by $\{\mathrm{CNOT}, R_z\}$, which account for a large fraction of operations and often dominate execution cost. This optimization can be challenging because phase-polynomial blocks are fragmented by basis-changing gates such as $H$, and optimizing phase parities alone may increase the cost of downstream basis transformations. Existing phase-polynomial approaches are limited to single-block or phase-only optimization, while subcircuit rewriting approaches are local and scale poorly beyond small rewrite windows. We introduce \emph{PhasePoly}, a compiler optimization pass that jointly optimizes phase-parity and output-parity networks and employs a cross-block intermediate representation to reuse parities across phase-polynomial block barriers. This approach is effective because its unified parity-matrix representation exposes long-range $\{\mathrm{CNOT}, R_z\}$ structure that local rewriting and single-block methods cannot capture. \emph{PhasePoly} reduces total gate count by up to 50.00\% (34.70\% on average) and CNOT count by up to 48.57\% (26.83\% on average), while scaling to large circuits and improving both fault-tolerant compilation and near-term hardware execution. \emph{PhasePoly} is available at https://github.com/ruadapt/PhasePoly.

cs.PL↗
arXiv2026

FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization

Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a Graph-Temporal-Causal Network that redefines the task from content recommendation to quantitative risk-return assessment. This architecture combines a relational graph encoder to capture the investment ecosystem's topology, a multi-scale temporal fusion module to handle long-term dependencies and non-stationarity, and a causal decision head that generates risk-adjusted predictions with interpretable causal attributions. A core innovation is the Meta-Causal Adaptation (MCA) strategy, which facilitates robust fine-tuning for new, data-scarce sectors by aligning updates with causally-plausible structures derived from meta-pretraining. Comprehensive experiments on proprietary VC datasets show that FinInvest-GTCN delivers state-of-the-art results, markedly lowering the primary Risk-Adjusted Mean Squared Error (RA-MSE) to 2.51 from a baseline of 3.05 and boosting the cumulative return of a simulated portfolio by 18.7\%. Ablation studies underscore the essential role of each component, while additional analyses confirm the model's stability, interpretability, and enhanced adaptability. This work pioneers a data-driven, explainable framework for investment decision support.

cs.CL↗
arXiv2026

EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control

Modern vision-language models (VLMs) for driving assistants typically treat vehicle dynamics as a black box, resulting in decisions that lack awareness of the vehicle's real-time electro-mechanical state. To bridge this gap, we introduce the Electro-Visual-Language Assistant (EVLA) -- a novel framework that combines multi-modal scene understanding with real-time perception of the electrified powertrain state (e.g., motor torque, battery SOC). Our approach features two key innovations: first, a Unified Co-State Encoder (UCSE) that fuses visual, textual, and vehicle-state inputs into a shared latent representation, augmented with an Energy-Efficiency Field to model spatial energy costs; and second, an Electro-aware Structured Reasoning Chain (ESRC), which replaces external chain-of-thought prompting with an internal, deterministic reasoning process grounded in physical constraints and optimization objectives. Trained end-to-end with a physics-guided joint loss, EVLA learns to generate context-aware and energy-optimal driving decisions. Extensive evaluations on a driving QA benchmark demonstrate that EVLA substantially outperforms strong fine-tuned VLM baselines, improving the final score by +0.0871 and accuracy by +5.6\%. Ablation studies validate the necessity of each component, and efficiency analyses show that EVLA achieves 36\% faster inference than multi-stage pipelines. This work underscores that integrating vehicle-state awareness and structured physical reasoning is crucial for developing next-generation, physically-grounded driving assistants.

cs.CL↗
arXiv2026

Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning

As large language models (LLMs) are increasingly deployed at the network edge to provide pervasive generative AI services, decentralized federated learning (DFL) provides a vital mechanism for privacy-preserving, domain-specific fine-tuning through peer-to-peer exchanges of parameter-efficient updates. However, the dynamic nature of practical decentralized edge networks, where devices may dynamically join or leave the collaborative training process, requires the system to continuously adapt to new data while selectively removing prior contributions. This correction process remains a significant bottleneck, as individual device updates become deeply entangled within the global fine-tuned parameters. To address this challenge, we propose a priority-aware learning-unlearning correction framework based on orthogonal LoRA that can enhance the knowledge evaluation through topology adjustment. Specifically, we first design an orthogonal LoRA mechanism that yields post-training contribution coordinates, enabling history-free projection addition and deletion in response to membership changes. We then analyze the correction bottleneck and develop a priority-aware policy that selects among topology refinement, local correction, proximal damping, and synchronization scheduling according to the dominant residual term. A resource allocation algorithm is further developed to allocate limited communication across layer groups, prioritizing the primary bottlenecks within per-round wireless constraints. Experiments demonstrate that the proposed framework achieves robust post-event correction for both device join and leave events and validate that different residual regimes necessitate distinct correction actions.

cs.LG↗
arXiv2026

Channel-Wise Mixed-Precision Quantization for Large Language Models

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter sizes. Weight-only quantization presents a promising solution to reduce the memory footprint of LLMs. However, existing approaches primarily focus on integer-bit quantization, limiting their adaptability to fractional-bit quantization tasks and preventing the full utilization of available storage space on devices. In this paper, we introduce Channel-Wise Mixed-Precision Quantization (CMPQ), a novel mixed-precision quantization method that allocates quantization precision in a channel-wise pattern based on activation distributions. By assigning different precision levels to different weight channels, CMPQ supports arbitrary average bit-widths in the low-bit regime (e.g., between 2 and 4 bits). CMPQ employs a non-uniform quantization strategy and incorporates two outlier extraction techniques that collaboratively preserve the critical information, thereby minimizing the quantization loss. Experiments on nine different LLMs demonstrate that CMPQ not only enhances performance in integer-bit quantization tasks but also achieves significant performance gains with a modest increase in memory usage by performing in a mixed-precision way. CMPQ represents an adaptive and effective approach to LLM quantization, offering substantial benefits across diverse device capabilities.

cs.CL↗
arXiv2026

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?

Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves nearly the same performance as training directly on the test sets, suggesting that the benchmarks cannot reliably separate further progress.To study this phenomenon, we introduce a diagnostic suite and the Oracle Performance Gap (OPG) metric that quantifies the performance difference between training on the train split versus the test split of a benchmark. We further analyze this phenomenon with stress tests and find that, despite strong benchmark scores, existing RL methods struggle to generalize across distribution shifts, varying levels of difficulty, and counterfactual scenarios: shortcomings that current benchmarks fail to reveal.We conclude that current benchmarks are insufficient for evaluating generalization and propose three core principles for designing more faithful benchmarks: sufficient difficulty, balanced evaluation, and distributional robustness.

cs.LG↗
arXiv2026

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs

Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benchmarks while demonstrating brittle reasoning capabilities on out-of-distribution (OOD) tasks. We term this phenomenon Reward-Induced Manifold Collapse. We establish a theoretical framework bridging Structural Causal Models (SCM) and the Information Bottleneck (IB) principle to explain this paradox. We define reasoning as a high-complexity causal process and shortcut learning as the exploitation of low-complexity spurious correlations. Under the implicit inductive bias of Stochastic Gradient Descent (SGD), models optimized for outcome rewards are biased toward shortcut solutions whenever the training distribution allows for a ``Markovian Screening'' of the true causal mechanism. We derive a new generalization bound based on Semantic Coverage Measure ($η$) rather than sample size, showing why data scaling on homogeneous distributions may fail to correct reasoning flaws. We also show that Process Reward Models (PRMs) function as Topological Filters, enforcing step-wise mutual information constraints that render the low-complexity shortcut manifold inadmissible. These results provide a mathematical grounding for the role of process supervision beyond simple credit assignment.

cs.LG↗
arXiv2026

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory

Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluations of LLM memory mostly rely on aggregate metrics such as final hold-out accuracy or cumulative online performance, which can obscure critical failure modes such as forgetting and negative transfer. In this paper, we introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving LLM memory. Drawing inspiration from continual learning, it targets a test-time setting in which memory is external, prompt-mediated, and updated without modifying model parameters. Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference. Specifically, it measures online utility, hold-out generalization, backward transfer, and forgetting, providing a finer-grained view of memory quality. Through extensive experiments across diverse tasks and memory methods, we show that higher final or cumulative accuracy does not necessarily imply better memory quality: many methods exhibit strong performance gains while suffering from substantial forgetting or negative transfer. Moreover, different memory designs exhibit distinct trade-offs between adaptability and stability that remain invisible under standard evaluation metrics.

cs.LG↗
arXiv2026

A Survey of Scaling in Large Language Model Reasoning

The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements achieved through scaling data and model size, the scaling of reasoning in LLMs is more complex and can even negatively impact reasoning performance, introducing new challenges in model alignment and robustness. In this survey, we provide a comprehensive examination of scaling in LLM reasoning, categorizing it into multiple dimensions and analyzing how and to what extent different scaling strategies contribute to improving reasoning capabilities. We begin by exploring scaling in input size, which enables LLMs to process and utilize a more extensive context for improved reasoning. Next, we analyze scaling in reasoning steps that improve multi-step inference and logical consistency. We then examine scaling in reasoning rounds, where iterative interactions refine reasoning outcomes. Furthermore, we discuss scaling in training-enabled reasoning, focusing on optimization through iterative model improvement. Finally, we outline future directions for further advancing LLM reasoning. By synthesizing these diverse perspectives, this survey aims to provide insights into how scaling strategies fundamentally enhance the reasoning capabilities of LLMs and further guide the development of next-generation AI systems.

cs.AI↗
arXiv2026

Verification of Machine Unlearning is Fragile

As privacy concerns escalate in the realm of machine learning, data owners now have the option to utilize machine unlearning to remove their data from machine learning models, following recent legislation. To enhance transparency in machine unlearning and avoid potential dishonesty by model providers, various verification strategies have been proposed. These strategies enable data owners to ascertain whether their target data has been effectively unlearned from the model. However, our understanding of the safety issues of machine unlearning verification remains nascent. In this paper, we explore the novel research question of whether model providers can circumvent verification strategies while retaining the information of data supposedly unlearned. Our investigation leads to a pessimistic answer: \textit{the verification of machine unlearning is fragile}. Specifically, we categorize the current verification strategies regarding potential dishonesty among model providers into two types. Subsequently, we introduce two novel adversarial unlearning processes capable of circumventing both types. We validate the efficacy of our methods through theoretical analysis and empirical experiments using real-world datasets. This study highlights the vulnerabilities and limitations in machine unlearning verification, paving the way for further research into the safety of machine unlearning.

cs.LG↗
arXiv2026

Testing holographic duality in hyperbolic lattices

The celebrated holographic duality posits a correspondence between a quantum gravity in a bulk spacetime and a quantum field theory (QFT) defined on its lower-dimensional boundary. This duality not only offers deep insights into the enigmatic nature of quantum gravity but also provides an efficient methodology for studying strongly correlated systems. However, despite its profound significance in modern physics, holographic duality remains a conjecture, and further experimental exploration is highly sought after. Here, we present the first experimental test of holographic duality between a three-dimensional bulk gravity and a two-dimensional boundary QFT using hyperbolic lattices. By experimentally measuring the classical scalar field propagator in hyperbolic circuits, we reproduce the equal-time two-point correlation function of the dual boundary conformal field theory (CFT), verifying its exponential dependence on the boundary separation and the conformal dimension-scalar mass relation. Furthermore, by leveraging the two-point correlation function, we reconstruct the entanglement entropy for a boundary CFT subsystem, confirming that it follows the Ryu-Takayanagi formula. These results constitute the first direct experimental evidence that quantum properties of the QFT can be holographically reproduced through its dual classical field in curved space. This heuristic experimental effort opens a new avenue for in-depth investigations on the holographic duality and extensive exploration of quantum-gravity-inspired phenomena in classical systems.

hep-lat↗
arXiv2026

Integrated Shape-Force Estimation for Continuum Robots: A Virtual-Work and Polynomial-Curvature Framework

Cable-driven continuum robots (CDCRs) are widely used in surgical and inspection tasks that require dexterous manipulation in confined spaces. Existing model-based estimation methods either assume constant curvature or rely on geometry-space interpolants, both of which struggle with accuracy under large deformations and sparse sensing. This letter introduces an integrated shape-force estimation framework that combines cable-tension measurements with tip-pose data to reconstruct backbone shape and estimate external tip force simultaneously. The framework employs polynomial curvature kinematics (PCK) and a virtual-work-based static formulation expressed directly in curvature space, where polynomial modal coefficients serve as generalized coordinates. The proposed method is validated through Cosserat-rod-based simulations and hardware experiments on a torque-cell-enabled CDCR prototype. Results show that the second-order PCK model achieves superior shape and force accuracy, combining a lightweight shape optimization with a closed-form, iteration-free force estimation, offering a compact and robust alternative to prior constant-curvature and geometry-space approaches.

cs.RO↗
arXiv2026

CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions

Instruction-based multimodal image manipulation has recently made rapid progress. However, existing evaluation methods lack a systematic and human-aligned framework for assessing model performance on complex and creative editing tasks. To address this gap, we propose CREval, a fully automated question-answer (QA)-based evaluation pipeline that overcomes the incompleteness and poor interpretability of opaque Multimodal Large Language Models (MLLMs) scoring. Simultaneously, we introduce CREval-Bench, a comprehensive benchmark specifically designed for creative image manipulation under complex instructions. CREval-Bench covers three categories and nine creative dimensions, comprising over 800 editing samples and 13K evaluation queries. Leveraging this pipeline and benchmark, we systematically evaluate a diverse set of state-of-the-art open and closed-source models. The results reveal that while closed-source models generally outperform open-source ones on complex and creative tasks, all models still struggle to complete such edits effectively. In addition, user studies demonstrate strong consistency between CREval's automated metrics and human judgments. Therefore, CREval provides a reliable foundation for evaluating image editing models on complex and creative image manipulation tasks, and highlights key challenges and opportunities for future research.

cs.CV↗
arXiv2026

CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models

Autoregressive large vision--language models (LVLMs) interface video and language by projecting video features into the LLM's embedding space as continuous visual token embeddings. However, it remains unclear where temporal evidence is represented and how it causally influences decoding. To address this gap, we present CircuitProbe, a circuit-level analysis framework that dissects the end-to-end video-language pathway through two stages: (i) Visual Auditing, which localizes object semantics within the projected video-token sequence and reveals their causal necessity via targeted ablations and controlled substitutions; and (ii) Semantic Tracing, which uses logit-lens probing to track the layer-wise emergence of object and temporal concepts, augmented with temporal frame interventions to assess sensitivity to temporal structure. Based on the resulting analysis, we design a targeted surgical intervention that strictly follows our observations: identifying temporally specialized attention heads and selectively amplifying them within the critical layer interval revealed by Semantic Tracing. This analysis-driven intervention yields consistent improvements (up to 2.4% absolute) on the temporal-heavy TempCompass benchmark, validating the correctness, effectiveness, and practical value of the proposed circuit-level analysis for temporal understanding in LVLMs.

cs.CV↗
arXiv2026

Joint User Association and Resource Allocation for Adaptive Semantic Communication in 5G and Beyond Networks

Semantic communication (SemCom) has emerged as a promising paradigm that leverages Deep Neural Networks (DNNs) to extract task-relevant information, thereby substantially reducing the volume of transmitted data. In existing implementations, the semantic transceiver is typically pre-trained for a specific task and uniformly adopted by all users. However, due to user heterogeneity in computational and communication capabilities, employing a single, fixed semantic transceiver may degrade the coding efficiency and transmission robustness. To address this issue, we first demonstrate the feasibility of dynamically adjusting the computational and communication overhead of DNN-based semantic transceivers, enabling a more flexible paradigm referred to as Adaptive Semantic Communication (ASC). Building on this concept, we formulate a joint user association and resource allocation problem for ASC in 5G and beyond networks, aiming to maximize overall system utility under energy and latency constraints. However, the problem is very challenging due to the inherent interdependencies among decision variables. To tackle this complexity, we decompose the original problem into three subproblems: (i) ASC scheme selection for each user, (ii) spectrum allocation at each Small-cell Base Station (SBS), and (iii) user association across SBSs. Each subproblem is solved sequentially based on the solutions of the preceding stages. The proposed algorithm efficiently yields near-optimal solutions with polynomial-time complexity. Simulation results demonstrate our approach outperforms existing baselines under various situations.

cs.NI↗
arXiv2026

Energy-Efficient Online Scheduling for Wireless Powered Mobile Edge Computing Networks

Wireless Powered Mobile Edge Computing (WP-MEC) integrates mobile edge computing (MEC) with wireless power transfer (WPT) to simultaneously extend the operational lifetime and enhance the computational capability of wireless devices (WDs). In WPMEC systems, WPT and computation offloading compete for limited wireless resources, which makes their joint scheduling particularly challenging. In this paper, we investigate the energy-efficient online scheduling problem for WPMEC networks with multiple WDs and multiple access points (APs). Based on Lyapunov optimization, we develop an online optimization framework that transforms the original stochastic problem into deterministic per-slot optimization problems. To reduce computational complexity, we introduce the concept of marginal energy efficiency and derive an associated optimality condition, based on which a relax-then-adjust approach is proposed to efficiently obtain feasible solutions. For the resulting non-convex computation offloading subproblem, we analyze the structural properties of its optimal solution and transform it into an assignment problem that can be solved efficiently. We further provide theoretical performance guarantees for both the per-slot and long-term solution, establishing a fundamental trade-off between latency and energy consumption. To improve practical performance, additional mechanisms are introduced to balance the magnitudes of different queues and reduce latency without increasing energy consumption. Extensive simulation results demonstrate the effectiveness and robustness of the proposed algorithm under various system settings.

cs.NI↗
arXiv2026

When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks

Online incivility has emerged as a widespread and persistent problem in digital communities, imposing substantial social and psychological burdens on users. Although many platforms attempt to curb incivility through moderation and automated detection, the performance of existing approaches often remains limited in both accuracy and efficiency. To address this challenge, we propose a Graph Neural Network (GNN) framework for detecting three types of uncivil behavior (i.e., toxicity, aggression, and personal attacks) within the English Wikipedia community. Our model represents each user comment as a node, with textual similarity between comments defining the edges, allowing the network to jointly learn from both linguistic content and relational structures among comments. We also introduce a dynamically adjusted attention mechanism that adaptively balances nodal and topological features during information aggregation. Empirical evaluations demonstrate that our proposed architecture outperforms 12 state-of-the-art Large Language Models (LLMs) across multiple metrics while requiring significantly lower inference cost. These findings highlight the crucial role of structural context in detecting online incivility and address the limitations of text-only LLM paradigms in behavioral prediction. All datasets and comparative outputs will be publicly available in our repository to support further research and reproducibility.

cs.CL↗
arXiv2026

A Cyclic Layerwise QAOA Training

The quantum approximate optimization algorithm (QAOA) is a hybrid quantum-classical algorithm for solving combinatorial optimization problems. Multi-angle QAOA (MA-QAOA), which assigns independent parameters to each Hamiltonian operator term, achieves superior approximation performance even with fewer layers than standard QAOA. Unfortunately, this increased expressibility can raise the classical computational cost due to a greater number of parameters. The recently proposed Layerwise MA-QAOA (LMA-QAOA) reduces this overhead by training one layer at a time, but it may suffer from obtaining the precise solution due to the previously fixed parameters. This work addresses two questions for efficient MA-QAOA training: (i) What is the optimal granularity for parameter updates per epoch, and (ii) How can we get precise final cost function results while only partially updating the parameters per epoch? Despite the benefit of reducing the parameters that update per epoch can reduce the classical computation overhead, too fine or coarse a granularity of Hamiltonian update can degrade the MA-QAOA training efficiency. We find that optimizing one complete layer per epoch is an efficient granularity. Moreover, selectively retraining each layer by tracking gradient variations can achieve a final cost function equivalent to the standard MA-QAOA while lowering the parameter update overhead. Based on these insights, we propose Orbit-QAOA, which cyclically revisits layers and selectively freezes stabilized parameters. Across diverse graph benchmarks, Orbit-QAOA reduces training steps by up to 81.8%, reduces approximation ratio error by up to 72x compared to the unified stop condition-applied enhanced LMA-QAOA, and achieves equivalent approximation performance compared to the standard MA-QAOA.

quant-ph↗